# AI Credits

## About AI credits

Every plan in Relay.app comes with a generous number of free AI credits. AI credits are a single pool of credits that are consumed when running steps that use AI, including:

* Prompting AI models
* Audio transcription and text-to-speech
* Image generation

The free AI credits that come with all our subscriptions are good for reasonable usage—see the tables below for more details and examples.

If you run out of AI credits in Relay.app, purchase more in your [billing settings](https://run.relay.app/settings/workspace/billing), or contact <support@relay.app> for help. Alternatively, if you already pay for credits with a AI service provider, connect that account to Relay.app and switch your AI automations to use that connected model.

### Free monthly AI credits per plan

<table><thead><tr><th width="155.33333333333331">Plan</th><th width="161" data-type="number">Free AI credits per month</th></tr></thead><tbody><tr><td><strong>Free</strong></td><td>500</td></tr><tr><td><strong>Professional</strong></td><td>2000</td></tr><tr><td><strong>Team</strong></td><td>2000</td></tr></tbody></table>

When the AI credits included in your plan aren't enough, it's easy to add more via the [billing page](https://run.relay.app/settings/workspace/billing). Note that you need to be on a paid plan in order to be able to add additional AI credits. If you're on a Free plan, upgrade to Professional or Team first.

### AI Credits conversion chart

*Updated: 2026-04-17*

<table><thead><tr><th width="304">AI Model / tool</th><th>1 AI credit is consumed for every...</th></tr></thead><tbody><tr><td>Text-to-speech (OpenAI TTS)</td><td>40 characters of text per AI credit</td></tr><tr><td>Text-to-speech (GPT-4o mini)</td><td>3 seconds of audio per AI credit</td></tr><tr><td>Text-to-speech (ElevenLabs)</td><td>1 characters of text per AI credit</td></tr><tr><td>Transcription: ElevenLabs (scribe)</td><td>4 seconds of audio per AI credit</td></tr><tr><td>Transcription: AssemblyAI (nano)</td><td>6 seconds of audio per AI credit</td></tr><tr><td>Transcription: AssemblyAI (best)</td><td>4 seconds of audio per AI credit</td></tr><tr><td>Transcription: (Groq - Whisper)</td><td>17 seconds of audio per AI credit</td></tr><tr><td>Transcription: OpenAI Whisper</td><td>6 seconds of audio per AI credit</td></tr><tr><td>Transcription: GPT-4o</td><td>6 seconds of audio per AI credit</td></tr><tr><td>Transcription: GPT-4o-mini</td><td>12 seconds of audio per AI credit</td></tr><tr><td>Text-to-speech (Cartesia - Sonic 2)</td><td>1 seconds of audio per AI credit</td></tr><tr><td>Transcription: (Cartesia - Ink Whisper)</td><td>12 seconds of audio per AI credit</td></tr><tr><td>Image generation: Imagen 3</td><td>50 AI credits per image</td></tr><tr><td>Image generation: Imagen 4</td><td>67 AI credits per image</td></tr><tr><td>Image generation: Imagen 4 Ultra</td><td>100 AI credits per image</td></tr><tr><td>Image generation: Imagen 4 Fast</td><td>33 AI credits per image</td></tr><tr><td>Video generation: Veo 3.1</td><td>5333 AI credits per 8 second video</td></tr><tr><td>Video generation: Veo 3.1 Fast</td><td>2000 AI credits per 8 second video</td></tr><tr><td>Video generation: Sora 2</td><td>1333 AI credits per 8 second video</td></tr><tr><td>Video generation: Sora 2 Pro</td><td>4000 AI credits per 8 second video</td></tr><tr><td>Image generation: DALL-E 3</td><td>HD, wide: 200 AI credits per image<br>HD: 140 AI credits per image<br>Basic quality, large: 140 AI credits per image<br>Basic quality: 70 AI credits per image</td></tr><tr><td>Image generation: GPT-Image-1</td><td><p>Square:</p><ul><li>278 AI credits per image</li><li>120 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>75 image <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>19 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul><p><br>Hi-res portrait / Landscape:</p><ul><li>417 AI credits per image</li><li>120 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>75 image <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>19 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul></td></tr><tr><td>Image generation: GPT-Image-1.5</td><td><p>Square:</p><ul><li>222 AI credits per image</li><li>120 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>60 image <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>15 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul><p><br>Hi-res portrait / Landscape:</p><ul><li>333 AI credits per image</li><li>120 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>60 image <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>15 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul></td></tr><tr><td>Image generation: Nano Banana (Gemini 2.5 Image Flash)</td><td><p>Nano Banana (Gemini 2.5 Image Flash):</p><ul><li>65 AI credits per image</li><li>2000 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul></td></tr><tr><td>Image generation: Nano Banana Pro (Gemini 3 Pro Image)</td><td><p>Gemini 3 Pro Image Preview (Nano Banana Pro):</p><ul><li>223 AI credits per output image (1K or 2K resolution)</li><li>400 AI credits per output image (4K resolution)</li><li>300 prompt <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li><li>112 AI credits per input image</li><li>50 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> per AI credit</li></ul></td></tr><tr><td>Claude Haiku 4.5</td><td>120 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>600 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>Claude Opus 4.7</td><td>24 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>120 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>Claude Sonnet 4.6</td><td>40 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>200 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>Gemini 3 Flash</td><td>200 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>1199 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>200 reasoning <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> (part of the output)</td></tr><tr><td>Gemini 3.1 Flash-Lite</td><td>400 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>2398 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>400 reasoning <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> (part of the output)</td></tr><tr><td>Gemini 3.1 Pro</td><td>50 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>300 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>50 reasoning <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> (part of the output)</td></tr><tr><td>Gemini Deep Research</td><td>50 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>300 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>50 reasoning <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> (part of the output)</td></tr><tr><td>GPT 5.4</td><td>40 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>240 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>GPT 5.4 mini</td><td>133 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>800 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>GPT 5.4 nano</td><td>480 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>2994 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>GPT 5.4 pro</td><td>3 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>20 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>Grok 4</td><td>40 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>200 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a></td></tr><tr><td>o3 deep research</td><td>15 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>60 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>17 credits for 1 web search</td></tr><tr><td>Perplexity Sonar</td><td>600 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>600 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>8 credits for 1 web search</td></tr><tr><td>Perplexity Deep Research</td><td>75 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>300 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>200 reasoning <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a> (part of the output)<br>8 credits for 1 web search</td></tr><tr><td>Perplexity Sonar Pro</td><td>40 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>200 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>10 credits for 1 web search</td></tr><tr><td>Perplexity Sonar Reasoning Pro</td><td>75 output <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>300 input <a href="https://docs.relay.app/ai/ai-credits#about-tokens">tokens</a><br>10 credits for 1 web search</td></tr></tbody></table>

## Track your AI credit usage

[This content has moved to a dedicated page.](https://docs.relay.app/workspace-and-account/step-and-ai-credit-usage)

## About tokens

The definition of a token differs slightly by model provider. Additionally, input and output tokens are also differentiated from a cost/consumption perspective. We suggest reading the short FAQs from each model provider to learn more:

* [Anthropic Claude](https://docs.anthropic.com/en/docs/resources/glossary#tokens)
* [Google Gemini](https://ai.google.dev/gemini-api/docs/tokens)
* [OpenAI GPT](https://help.openai.com/en/articles/4936856-what-are-tokens-and-how-to-count-them)

Unfortunately, it's not trivial to predict how many tokens an AI step will consume upfront, although the articles linked above will give you a better understanding.

For AI steps in Relay.app, token usage is primarily influenced by these factors:

* **Context included in the prompt**\
  The more and larger the attached context, the more tokens will be used every time your step is executed. For example:
  * An email can easily increase token usage by a few thousand
  * A PDF can go way beyond that, depending on the size\\
* **Whether the step is given Internet access**\
  All text on the websites that the model needs to visit for your prompt is included as context, including user-hidden HTML. This can be anywhere between a few hundred to tens of thousands of tokens used per step execution, depending on how many websites the model needs to visit and how large they are.